用多个先进模型的集成，提升深伪检测在不同数据集上的稳定性。
Ensemble-Based Deepfake Detection using State-of-the-Art Models with Robust Cross-Dataset Generalisation
- 采用多个顶级模型的预测概率进行集成，不依赖单一模型。
- 在两个跨数据集测试中，集成方法性能更稳定，无一模型始终领先。
- 适合真实场景中未知伪造类型或质量时的检测需求。
基于机器学习的深伪检测模型在基准数据集上表现优异，但在分布外数据上的性能常大幅下降。本文研究一种基于集成的方法，以提升深伪检测系统在多样化数据集上的泛化能力。基于最新开源基准，我们结合了来自顶级会议的若干先进非对称模型的预测概率。实验涵盖两个不同的分布外数据集，结果表明：任一模型在所有场景中均未持续领先；而集成预测在所有情况下均表现出更稳定、可靠的性能。研究提示，非对称集成提供了一种鲁棒且可扩展的解决方案，适用于真实世界中伪造类型或质量未知的深伪检测场景。
原文摘要 · Abstract (English)
Machine learning-based Deepfake detection models have achieved impressive results on benchmark datasets, yet their performance often deteriorates significantly when evaluated on out-of-distribution data. In this work, we investigate an ensemble-based approach for improving the generalization of deepfake detection systems across diverse datasets. Building on a recent open-source benchmark, we combine prediction probabilities from several state-of-the-art asymmetric models proposed at top venues. Our experiments span two distinct out-of-domain datasets and demonstrate that no single model consistently outperforms others across settings. In contrast, ensemble-based predictions provide more stable and reliable performance in all scenarios. Our results suggest that asymmetric ensembling offers a robust and scalable solution for real-world deepfake detection where prior knowledge of forgery type or quality is often unavailable.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。